CN109885063A - A kind of application robot farmland paths planning method merging vision and laser sensor - Google Patents
A kind of application robot farmland paths planning method merging vision and laser sensor Download PDFInfo
- Publication number
- CN109885063A CN109885063A CN201910201270.1A CN201910201270A CN109885063A CN 109885063 A CN109885063 A CN 109885063A CN 201910201270 A CN201910201270 A CN 201910201270A CN 109885063 A CN109885063 A CN 109885063A
- Authority
- CN
- China
- Prior art keywords
- robot
- farmland
- path
- application
- application robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
A kind of application robot farmland paths planning method for merging vision and laser sensor is disclosed herein.Specifically: acquisition field boundary line and crop row information first are fitted field boundary line using least square method；Further according to information such as pesticide applicator operating direction spraying swath, minimum turning radius, working region is divided using Grid Method, the round-trip formulation rate of fusion application robot and fuel consumption, the information such as medical fluid surplus and fuel oil surplus estimate pesticide and fuel oil supply point position；Field image finally is acquired using visual sensor, extracts farmland center path, routing information progress coordinate conversion is updated into global path and calculates Navigation Control parameter；Simultaneously using laser sensor real time scan, acquisition obstacle position information to judge the avoidance mode of robot, if avoidance need to be turned to, avoidance route is planned using Artificial Potential Field Method, further updates global route.
Description
Technical field
The invention mainly relates to paths planning methods, and in particular to be it is a kind of merge vision and laser sensor application
Robot farmland paths planning method.
Background technique
With the development of precision agriculture, China sowing, application, fertilising and in terms of agricultural equipment it is automatic
Change, mechanization have reached higher level, and operating efficiency is significantly improved；But pilot steering operation is still needed, especially
For large-scale farmland, long working easily leads to driver tired driving, causes operating efficiency to reduce, crop damage, application people
Phenomena such as member is poisoned.The purpose of autonomous navigation technology is that substitution personnel drive, and mitigates operating personnel's working strength, improves work
Make efficiency, therefore in occupation of critical role in the technical system of precision agriculture.Path Planning Technique is to realize spray robot
The premise of AUTONOMOUS TASK realizes that independent navigation plays a key effect to robot.Path planning includes global path planning drawn game
Portion's path planning, guidance path of how accurately making rational planning for out, it has also become the focus and emphasis of domestic and international mechanism.
In the independent navigation of reading intelligent agriculture equipment, Global motion planning and sector planning are primarily to solve the problems, such as.Document is " more
The research of sortie operation plant protection drone least energy consumption Path Planning " (Xu Bo, Chen Liping, Tan or wait agricultural mechanical journal,
2015,46 (11): 36-42) select elemental operation side of the reciprocal traversal as unmanned plane in complete coverage path planning method
Formula, after obtaining the service line of unmanned plane using grating map building method, from the constraint conditions such as total energy consumption and operating efficiency,
The load medicine and spray value of each sortie of reasonable distribution, and the flight course planning algorithm of autonomous plant protection drone is further studied, make to return
Course line rood is to preferably planning；But due to the influence of environmental factor and GPS positioning error, there is course-line deviation, and do not have
There is the avoidance problem for considering the barriers such as farmland electric pole.Document " self-navigation Field-working Tractor-implement path planning and application
Test " (Wang Jianbo, the agricultural research such as Zhao Yuqin, Zhu Chenhui, 2017 (2): 242-245) analysis Field-working Tractor-implement
All region covering paths planning method proposes to carry out optimizing to tractor driving path using fully intermeshing algorithm, according to turning road
The tractor that diameter determines is taken up space, and farmland is divided into straight line operating area and headland turn region.For the former, with turning
Number at least determines the relative direction in farmland of straight line path；For the latter, with the most short determination of turning path time-consuming to straight line
The traversal order in path and mode of turning accordingly, improve the operability of path planning amplification, but do not consider local avoidance
Turning mode.(south China Huang little Gang science and engineering is big for document " studying with parameter acquiring method in paddy field weed-killer robot visual guidance path "
Learn, 2012) a kind of paddy field weed-killer robot rice shoot recognizer is proposed, this method is using K-means algorithm to rice shoot feature
It is analyzed, extract the characteristic point of rice shoot using window statistic law and carries out clustering, fitted by Hough transform method
Navigation center's line, and calculating drift angle and lateral deviation respectively by coordinate transform is 1.1 °, 4.1mm, substantially meets local road
The requirement of diameter planning.
Summary of the invention
The present invention is in view of the above problems, propose application robot, path, the farmland rule of a kind of fusion vision and laser sensor
The method of drawing.Field boundary line and crop row information are obtained first, are fitted field boundary line using least square method；Further according to application
The information such as machine operation direction spraying swath, minimum turning radius divide working region using Grid Method, and fusion application robot applies back and forth
Dose and fuel consumption, the information such as medical fluid surplus and fuel oil surplus estimate pesticide and fuel oil supply point position；Finally utilize vision
Sensor acquires field image, extracts farmland center path, and routing information is carried out coordinate conversion update global path and is calculated
Navigation Control parameter out；Simultaneously using laser sensor real time scan, acquisition obstacle position information to judge keeping away for robot
Barrier mode plans avoidance route using Artificial Potential Field Method, further updates global path line if avoidance need to be turned to.
The purpose of the present invention is: it is all based on remote control for current most of plant protection drone, it is real there is no realizing
It is unmanned, and the effect is unsatisfactory for manual remote control operation；Existing farmland paths planning method is mainly all standing
Paths planning method instructs farm machinery navigation by GPS coordinate acquisition system, but does not account for unmanned plane continuation of the journey, avoidance and rule
Situations such as path drawn and practical farmland path offset, corresponding solution is proposed, to cook up minimum for plant protection drone
The guidance path of deviation, and realize real-time deviation correcting, avoidance, fixed point pesticide or fuel oil supply etc. functions, further increase plant protection without
Man-machine operation's efficiency.
A kind of technical solution of invention are as follows: farmland path planning side, application robot for merging vision and laser sensor
Method, comprising the following steps:
Step 1: farmland high-precision boundary line and crop line position being obtained using manual measurement method in farmland target job region
Confidence breath；
Step 2: extracting field boundary location information, boundary line fitting is in line using least square method；According to application
Robot spraying swath width is by operating area rasterizing；
Step 3: according to the farmland length and width of operating direction, the round-trip one time formulation rate of fusion application robot, medicine
The information such as liquid surplus, power consumption, battery capacity and turning radius, planning application robot global path line simultaneously estimate pesticide
With fuel oil supply point position；
Step 4: acquiring farmland image in real time using monocular-camera, pass through pretreatment, Gaussian Blur denoising, image segmentation
Farmland path is extracted in equal operations, extracts guidance path with improved parallel thinning algorithm, and routing information is carried out coordinate conversion
Afterwards, it updates global path and calculates Navigation Control parameter；
Step 5: using laser sensor real time scan and obtaining the obstacle position information in rice field, extract application machine
Obstacle position information within the spray bar length of people unilateral side, according to barrier and application robot operating direction vertical line distance L,
Select avoidance mode；
Step 6: if barrier described in step 5 and application robot operating direction vertical line distance(d is application
Robot vehicle width), it is administered robot combination minimum turning radius, avoidance path, target point setting are planned using Artificial Potential Field Method
For vertical line described in step 5 and the intersection point of operating direction and along driving direction 5m；
Step 7: if the range of barrier described in step 5 and application robot operating direction vertical line distance L is(d is application robot vehicle width, and m is pesticide applicator spraying swath), application robot recycles spray boom avoidance, and wherein d is application
The vehicle width of machine, m are pesticide applicator spraying swath；
Step 8: the avoidance path-line information obtained according to step 6 updates global path line described in step 4.
Further, farmland edge fitting and region rasterizing process in the step 2 are as follows: obtain man-hour manually hand-held GPS around
Four edges circle fitting in farmland is in line respectively with least square method, and calculates by field boundary one week all coordinate informations
The frontier distance length being fitted, foundation are administered robot manipulating task spraying swath, crop line direction and farmland entrance for operation area
Domain rasterizing.
Further, the detailed process of the step 3 are as follows:
Step 3.1: application robot global path line determines method are as follows: passes through the calculated farmland length a of step 2 and width
B is spent, minimum turning radius R, planning application robot global road are calculated by the equal differential steering model of analysis pesticide applicator front and back wheel
Line.
The calculation formula of minimum turning radius R in step 3.1 described further are as follows:
Wherein: wheel base before and after L-
The corresponding wheelspan in the angle a- α
The corresponding wheelspan in the angle b- β
α-chassis first half ideal Ackermann-Jeantand steering model steering angle
β-chassis latter half ideal Ackermann-Jeantand steering model steering angle.
Step 3.2: application robot pesticide and fuel oil supply point location determining method are as follows: calculate unmanned application machine operation away from
Formulation rate when from for aWith fuel consumption VQ2, unmanned plane medicine-chest and fuel tank surplus information are read in real time, when unmanned plane medicine-chest
Or the surplus of fuel tank is less thanOr 2VQ2When, it is set as pesticide supply point P or fuel oil supply point position Q；
Further, the detailed process of the step 4 are as follows:
Step 4.1: acquiring field image in real time using monocular-camera, convert images into HSI color space, and carry out
Gaussian Blur processing, then Threshold segmentation processing is carried out to channel S image, extract farmland route characteristic；
Step 4.2: Morphological scale-space being carried out to the image after segmentation, passes through the threshold traits such as setting regions area, width
Extract intermediate path region；
Step 4.3: convex closure processing being carried out to intermediate passage zone, removes edges of regions projecting point, fill path region, fortune
Center line is extracted with improved parallel thinning algorithm, center line information is subjected to coordinate conversion and updates global route；
Further, avoidance mode selection method in the step 5 are as follows: according to Obstacle Position O (S, θ), calculate barrier
With the calculation formula of application robot operating direction vertical line distance L are as follows: L=Ssin θ, wherein S is barrier and application machine
The linear distance of people, θ are the angle for being administered robot operating direction and barrier.WhenWhen, show barrier in pesticide applicator
Front, selection turning avoidance mode；WhenWhen, select avoidance mode of putting away sports equipment.
Further, Artificial Potential Field Method step detailed process in the step 6 are as follows:
Step 6.1: founding mathematical models initialize all parameters of Artificial Potential Field Method formula, comprising: gravitation gain coefficient
ka, repulsion gain coefficient kr, barrier coverage ρ0, robot speed v, robot starting point W, Obstacle Position O, machine
People's target point Wg。
Step 6.2: the angle γ of resultant force size suffered by calculating robot and resultant force and horizontal direction.
Step 6.3: the position that calculating robot moves in next step, calculation formula are as follows:
Xi+1=Xi+vcosγ
Yi+1=Yi+vsinγ
Step 6.4: robot is moved to (XI+1,Yi+1), after robot one step of every operation, step number i=i+1, robot
Position is by (Xi, Yi) become (XI+1,Yi+1)。
Step 6.5: when robot reaches in the range of aiming spot place, being considered as obstacle-avoiding route planning success, then
Determine that robot reaches target point, when robot does not reach in target point location, then return step 6.2 continues to move.
Further, mesh calibration method of putting away sports equipment is determined in the step 7 are as follows: according to the range of θ, specifically judge left spray boom recycling
Or right spray boom recycling or left and right spray boom recycle simultaneously.
The advantages of this programme, is:
1) compared with existing farmland paths planning method, the present invention merges application robot one way formulation rate, one way consumption
The information such as electricity, residual volume of solution, fuel oil surplus and turning radius, planning application robot global path line, and estimate pesticide
With fuel oil supply point position, prevents application robot from occurring pesticide during farm work and lack or cause to stop because being short of power
Only operation phenomenon occurs.
2) it merges vision guided navigation and laser sensor avoidance realizes local paths planning and real-time update global path planning
Line improves application robot navigation accuracy.
3) intermediate path region in farmland is extracted using machine vision method, extracts center using improved parallel thinning algorithm
Routing information is coordinately transformed and updates global path planning line, and is converted into Navigation Control parameter by path-line, meets
Under GPS signal deviation is larger or loss situation, correction application robot direction of travel improves the robustness of system.
4) it utilizes laser sensor real time scan and obtains the obstacle position information in rice field, extract application robot list
Obstacle position information within side spray pole length, according to the vertical line distance L of barrier and application robot operating direction, selection
Avoidance mode gives barrier repulsion coverage, and by putting away sports equipment, avoidance mode reduces unnecessary obstacle-avoiding route planning, improves
Operating efficiency.
Detailed description of the invention
Fig. 1 is path planning process figure of the present invention.
Fig. 2 is the Path Recognition flow chart based on machine vision.
Fig. 3 is the location diagram for being administered robot and barrier.
Fig. 4 is the equal differential steering model of pesticide applicator front and back wheel.
Specific embodiment
As shown in Figure 1, a kind of application robot farmland paths planning method for merging vision and laser sensor, specific to walk
Suddenly are as follows:
Step 1: farmland high-precision boundary line and crop line position being obtained using manual measurement method in farmland target job region
Confidence breath；
Step 2: extracting field boundary location information, boundary line fitting is in line using least square method；According to application
Robot spraying swath width is by operating area rasterizing；Farmland edge fitting and region rasterizing process in the step 2 are as follows: obtain
It takes man-hour manually hand-held GPS around field boundary one week all coordinate informations, respectively intends farmland four edges circle with least square method
Straight line, and the frontier distance length that digital simulation is good are synthesized, according to application robot manipulating task spraying swath, crop line direction and farmland
Entrance is by operating area rasterizing.
Step 3: according to the farmland length and width of operating direction, the round-trip one time formulation rate of fusion application robot, medicine
The information such as liquid surplus, power consumption, battery capacity and turning radius, planning application robot global path line simultaneously estimate pesticide
With fuel oil supply point position；The detailed process of the step 3 are as follows:
Step 3.1: application robot global path line determines method are as follows: passes through the calculated farmland length a of step 2 and width
B is spent, minimum turning radius R, planning application robot global road are calculated by the equal differential steering model of analysis pesticide applicator front and back wheel
Line.
Fig. 4 is the equal differential steering model of pesticide applicator front and back wheel.Wherein: L indicates that front and back wheel base, a indicate the corresponding wheel in the angle α
Away from b indicates that the corresponding wheelspan in the angle β, α indicate the steering of chassis first half ideal Ackermann-Jeantand steering model
Angle, β indicate the steering angle of chassis latter half ideal Ackermann-Jeantand steering model, V1、V2、V3And V4Respectively
Represent the angular speed of four wheels.
The calculation formula of minimum turning radius R in step 3.1 described further are as follows:
Wherein: wheel base before and after L-
The corresponding wheelspan in the angle a- α
The corresponding wheelspan in the angle b- β
α-chassis first half ideal Ackermann-Jeantand steering model steering angle
β-chassis latter half ideal Ackermann-Jeantand steering model steering angle.
Step 3.2: application robot pesticide and fuel oil supply point location determining method are as follows: calculate unmanned application machine operation away from
Formulation rate when from for aWith fuel consumption VQ2, unmanned plane medicine-chest and fuel tank surplus information are read in real time, when unmanned plane medicine-chest
Or the surplus of fuel tank is less thanOr 2VQ2When, it is set as pesticide supply point P or fuel oil supply point position Q；
Step 4: acquiring farmland image in real time using monocular-camera, pass through pretreatment, Gaussian Blur denoising, image segmentation
Farmland path is extracted in equal operations, extracts guidance path with improved parallel thinning algorithm, and routing information is carried out coordinate conversion
Afterwards, it updates global path and calculates Navigation Control parameter；(as shown in Figure 2)
The detailed process of the step 4 are as follows: (detailed process such as: application No. is 201810441889.5 patents of invention " one
Kind farmland spray machine device people's vision guided navigation path identification method ")
Step 4.1: field image is acquired in real time using monocular-camera, by using the trans_ that Halcon is packaged
Original image is converted into HSI color space from RGB color by from_rgb operator；In order to solve to make in the long narrow path in farmland
Object intersects occlusion issue, after determining sigma value, is carried out at Gaussian Blur by gen_gauss_filter operator to HSI image
Reason, then according to farmland path gray feature in channel S image, Threshold segmentation processing is carried out, extract farmland path；
Step 4.2: Morphological scale-space being carried out to the image after segmentation, the threshold traits such as setting regions area, width extract
Intermediate path region；
Step 4.3: with the shape_trans operator in Halcon, selecting ' convex ' characterization factor to intermediate path
Region carries out convex closure processing, edges of regions projecting point and fill path region is effectively removed, with improved parallel thinning algorithm
Center line is extracted, after being demarcated according to camera parameters, center line information is subjected to coordinate conversion and updates global route.It is improved simultaneously
Three step iteration of row thinning algorithm point or less is handled:
1) label meets the black pixel point P of condition；First step algorithmic formula:
3≤B(P)≤6
XR(P)=2
P1×P3×P5=0
P1×P3×P7=0
The adjacent number of the non-zero of P: B (p)=p1+p2+…+P8
The crossing number of P:Wherein p9=p1
2) judge P point whether be line both ends.As fruit dot P meets formula (8), then it represents that point P is not endpoint, carries out step
3；Otherwise retention point P, return step 1 carry out the judgement of next P point.
3) P point is deleted.If labeled point P meets algorithm requirement, point P will be directly deleted；Third step algorithm is public
Formula:
P1×P5×P7=0
P3×P5×P7=0
Step 5: using laser sensor real time scan and obtaining the obstacle position information in rice field, extract application machine
Obstacle position information within the spray bar length of people unilateral side, according to barrier and application robot operating direction vertical line distance L,
Select avoidance mode；
Avoidance mode selection method in the step 5 are as follows: according to Obstacle Position O (S, θ), calculate barrier and pesticide applicator
The calculation formula of device people's operating direction vertical line distance L are as follows: L=Ssin θ, wherein S is barrier and the straight line for being administered robot
Distance, θ are the angle for being administered robot operating direction and barrier.WhenWhen, show barrier pesticide applicator just before
Side, selection turning avoidance mode；WhenWhen, select avoidance mode of putting away sports equipment.
Fig. 3 is the location diagram for being administered robot and barrier.Wherein: A point indicates application robot center, O
Point indicates that Obstacle Position, the intersection point of point B expression point O to the application robot driving direction shortest distance, S indicate barrier and apply
The distance of medicine robot, θ indicate barrier and the angle for being administered the robot direction of motion, and m indicates the length of CD, i.e. pesticide applicator sprays
Width.
Step 6: if barrier described in step 5 and application robot operating direction vertical line distance(d is application
Robot vehicle width), it is administered robot combination minimum turning radius, avoidance path, target point setting are planned using Artificial Potential Field Method
For vertical line described in step 5 and the intersection point of operating direction and along driving direction 5m；
Artificial Potential Field Method detailed process in the step 6 are as follows:
Step 6.1: founding mathematical models initialize all parameters of Artificial Potential Field Method formula, comprising: gravitation gain coefficient
ka, repulsion gain coefficient kr, barrier coverage ρ0, robot speed v, robot starting point W, Obstacle Position O, machine
People's target point Wg。
Step 6.2: the angle γ of resultant force size suffered by calculating robot and resultant force and horizontal direction.
Step 6.3: the position that calculating robot moves in next step, calculation formula are as follows:
Xi+1=Xi+vcosγ
Yi+1=Yi+vsinγ
Step 6.4: robot is moved to (Xi+1, Yi+1), after robot one step of every operation, step number i=i+1, robot
Position is by (Xi, Yi) become (Xi+1, Yi+1)。
Step 6.5: when robot reaches in the range of aiming spot place, being considered as obstacle-avoiding route planning success, then
Determine that robot reaches target point, when robot does not reach in target point location, then return step 6.2 continues to move.
Step 7: if the range of barrier described in step 5 and application robot operating direction vertical line distance L is(d is application robot vehicle width, and m is pesticide applicator spraying swath), application robot recycles spray boom avoidance, and wherein d is application
The vehicle width of machine, m are pesticide applicator spraying swath；
The method put away sports equipment is determined in the step 7 are as follows: according to the range of θ, specifically judge that left spray boom recycling or right spray boom are returned
It receives or left and right spray boom recycles simultaneously.
Step 8: the avoidance path-line information obtained according to step 6 updates global path line described in step 4.
Claims (7)
1. a kind of application robot farmland paths planning method for merging vision and laser sensor, which is characterized in that specific step
Suddenly are as follows:
Step 1: farmland high-precision boundary line and crop row position being obtained using manual measurement method in farmland target job region and believed
Breath；
Step 2: extracting field boundary location information, boundary line fitting is in line using least square method；According to application machine
People's spraying swath width is by operating area rasterizing；
Step 3: according to the length and width in operating direction farmland, the round-trip one time formulation rate of fusion application robot, residual volume of solution,
The information such as power consumption, battery capacity and turning radius, planning application robot global path line simultaneously estimate pesticide and fuel oil benefit
To a position；
Step 4: acquiring farmland image in real time using monocular-camera, grasped by pretreatment, Gaussian Blur denoising, image segmentation etc.
Make to extract farmland path, extract guidance path with improved parallel thinning algorithm, routing information is subjected to coordinate conversion and is updated
Global path simultaneously calculates Navigation Control parameter；
Step 5: using laser sensor real time scan and obtaining the obstacle position information in rice field, extract application robot list
Obstacle position information (angle θ, distance are S) within side spray pole length, according to barrier and application robot operator
To vertical line distance L, select avoidance mode；
Step 6: if (d is application machine by barrier described in step 5 and application robot operating direction vertical line distance L≤d/2
People's body width), it is administered robot combination minimum turning radius, avoidance path, target point setting are planned using Artificial Potential Field Method
For the intersection point of Global motion planning line and field boundary where application robot driving direction；
Step 7: if the range of barrier described in step 5 and application robot operating direction vertical line distance L is
(d is application robot vehicle width, and m is pesticide applicator spraying swath), application robot recycles spray boom avoidance, according to barrier described in step 5
Angle, θ range determines recycling left side spray boom or recycling right side spray boom；
Step 8: the avoidance path-line information obtained according to step 6 updates global path line described in step 4.
2. a kind of farmland path planning side, application robot for merging vision and laser sensor according to claim 1
Method, which is characterized in that extract field boundary location information in the step 2, be fitted to boundary line directly using least square method
Line；Foundation is administered robot spraying swath width for operating area rasterizing.
3. a kind of farmland path planning side, application robot for merging vision and laser sensor according to claim 1
Method, which is characterized in that the detailed process of the step 3 are as follows:
Step 3.1: application robot global path line determines method are as follows: by step 2 calculated farmland length a and width b,
Minimum turning radius R, planning application robot global route are calculated by the equal differential steering model of analysis pesticide applicator front and back wheel.Most
The calculation formula of tight turn radius R are as follows:
α=β
Wherein: L-front and back wheel base；The corresponding wheelspan in the angle a-α；The corresponding wheelspan in the angle b-β；α-chassis first half sub-argument
Think the steering angle of Ackermann-Jeantand steering model；β-chassis latter half ideal Ackermann-Jeantand
The steering angle of steering model.
Step 3.2: application robot pesticide and fuel oil supply point location determining method are as follows: calculating unmanned application machine operation distance is
Formulation rate Vp when a1With fuel consumption VQ2, unmanned plane medicine-chest and fuel tank surplus information are read in real time, when unmanned plane medicine-chest or oil
The surplus of case is less than 2Vp1Or 2VQ2When, it is set as pesticide supply point P or fuel oil supply point position Q.
4. a kind of farmland path planning side, application robot for merging vision and laser sensor according to claim 1
Method, which is characterized in that the detailed process of the step 4 are as follows:
Step 4.1: acquiring field image in real time using monocular-camera, convert images into HSI color space, and carry out Gauss
Fuzzy Processing, then Threshold segmentation processing is carried out to channel S image, extract farmland route characteristic；
Step 4.2: Morphological scale-space being carried out to the image after segmentation, is extracted by threshold traits such as setting regions area, width
Intermediate path region；
Step 4.3: convex closure processing being carried out to intermediate passage zone, removes edges of regions projecting point, fill path region, with changing
Into parallel thinning algorithm extract center line, center line information is subjected to coordinate conversion and updates global route；
5. a kind of farmland path planning side, application robot for merging vision and laser sensor according to claim 1
Method, which is characterized in that avoidance mode selection method in step 5 are as follows: according to Obstacle Position O (S, θ), calculate barrier and application
The calculation formula of robot manipulating task direction vertical line distance L are as follows: L=Ssin θ, wherein S be barrier with application robot it is straight
Linear distance, θ are the angle for being administered robot operating direction and barrier, whenWhen, show barrier pesticide applicator just before
Side, selection turning avoidance mode；WhenWhen, select avoidance mode of putting away sports equipment.
6. a kind of farmland path planning side, application robot for merging vision and laser sensor according to claim 1
Method, which is characterized in that Artificial Potential Field Method detailed process in the step 6 are as follows:
Step 6.1: founding mathematical models initialize all parameters of Artificial Potential Field Method formula, comprising: gravitation gain coefficient ka, repulsion
Gain coefficient kr, barrier coverage ρ0, robot speed v, robot starting point W, Obstacle Position O, robot target point
Wg；
Step 6.2: the angle γ of resultant force size suffered by calculating robot and resultant force and horizontal direction；
Step 6.3: the position that calculating robot moves in next step, calculation formula are as follows:
Xi+1=Xi+vcosγ
Yi+1=Yi+vsinγ
Step 6.4: robot is moved to (Xi+1,Yi+1), after robot one step of every operation, step number i=i+1, the position of robot
By (Xi,Yi) become (Xi+1,Yi+1)。
Step 6.5: when robot reaches in the range of aiming spot place, being considered as obstacle-avoiding route planning success, then determine
Robot reaches target point, and when robot does not reach in target point location, then return step 6.2 continues to move.
7. a kind of farmland path planning side, application robot for merging vision and laser sensor according to claim 1
Method, which is characterized in that the method put away sports equipment is determined in the step 7 are as follows: according to the range of θ, specifically judge left spray boom recycling or right
Spray boom recycling or left and right spray boom recycle simultaneously.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201270.1A CN109885063A (en) | 2019-03-15 | 2019-03-15 | A kind of application robot farmland paths planning method merging vision and laser sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201270.1A CN109885063A (en) | 2019-03-15 | 2019-03-15 | A kind of application robot farmland paths planning method merging vision and laser sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109885063A true CN109885063A (en) | 2019-06-14 |
Family
ID=66932657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910201270.1A Pending CN109885063A (en) | 2019-03-15 | 2019-03-15 | A kind of application robot farmland paths planning method merging vision and laser sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109885063A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110296698A (en) * | 2019-07-12 | 2019-10-01 | 贵州电网有限责任公司 | It is a kind of with laser scanning be constraint unmanned plane paths planning method |
| CN110411452A (en) * | 2019-08-12 | 2019-11-05 | 西北农林科技大学 | A kind of farmland spray machine device people's navigation path identification method based on binocular vision |
| CN110428664A (en) * | 2019-09-09 | 2019-11-08 | 湖南科技大学 | Traffic avoiding collision based on computer vision human bioequivalence |
| CN110426045A (en) * | 2019-08-12 | 2019-11-08 | 西北农林科技大学 | A kind of farmland spray machine device people vision guided navigation parameter acquiring method |
| CN110609570A (en) * | 2019-07-23 | 2019-12-24 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Autonomous obstacle avoidance inspection method based on unmanned aerial vehicle |
| CN111007850A (en) * | 2019-12-06 | 2020-04-14 | 首都师范大学 | Agricultural machine control method, device and equipment based on field operation |
| CN111506062A (en) * | 2020-03-30 | 2020-08-07 | 江苏大学 | Full-automatic pesticide applying ship and uniform pesticide spraying method |
| CN111506105A (en) * | 2020-04-08 | 2020-08-07 | 安徽舒州农业科技有限责任公司 | Agricultural unmanned aerial vehicle control device and sowing control method |
| CN111596652A (en) * | 2019-12-30 | 2020-08-28 | 山东省科学院自动化研究所 | Pesticide spraying intelligent agricultural machinery path finding navigation control method and system |
| CN111796283A (en) * | 2020-07-13 | 2020-10-20 | 江苏恒澄交科信息科技股份有限公司 | Millimeter wave radar noise reduction method based on route |
| CN112000131A (en) * | 2020-09-09 | 2020-11-27 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster path planning method and system based on artificial potential field method |
| CN112526983A (en) * | 2020-09-11 | 2021-03-19 | 深圳市银星智能科技股份有限公司 | Robot path planning method, master control chip and robot |
| CN112596518A (en) * | 2020-12-07 | 2021-04-02 | 深圳拓邦股份有限公司 | Robot cleaning path planning method and device and floor washing robot |
| CN113112209A (en) * | 2021-05-13 | 2021-07-13 | 浙江万里学院 | Logistics distribution safety protection method for acquiring real-time movement track of goods |
| CN113179826A (en) * | 2021-04-30 | 2021-07-30 | 梁世军 | Application technology of pesticide on water surface |
| CN113459090A (en) * | 2021-06-15 | 2021-10-01 | 中国农业大学 | Intelligent obstacle avoiding method of palletizing robot, electronic equipment and medium |
| CN113778081A (en) * | 2021-08-19 | 2021-12-10 | 中国农业科学院农业资源与农业区划研究所 | Orchard path identification method and robot based on laser radar and vision |
| CN113791625A (en) * | 2021-09-30 | 2021-12-14 | 深圳市优必选科技股份有限公司 | Full coverage path generation method and device, terminal equipment and storage medium |
| CN113799129A (en) * | 2021-09-17 | 2021-12-17 | 吉林省农业机械研究院 | Barrier control system is kept away to spray lance formula laxative machine arm intelligence |
| CN114326717A (en) * | 2021-12-13 | 2022-04-12 | 中国科学院计算技术研究所 | Intelligent agricultural machinery transition and operation fusion path planning method and system |
| CN114680097A (en) * | 2022-06-02 | 2022-07-01 | 农业农村部南京农业机械化研究所 | Spraying machine pesticide application positioning method based on monitoring data acquisition and processing |
| CN116225072A (en) * | 2023-05-09 | 2023-06-06 | 济宁市兖州区同瑞机械有限公司 | Route real-time planning management system suitable for agricultural transport machine |
| CN116609278A (en) * | 2023-07-21 | 2023-08-18 | 华东交通大学 | Method and system for collecting farmland heavy metal spectrum data |
| CN116965393A (en) * | 2023-09-22 | 2023-10-31 | 安徽农业大学 | High-clearance variable-track plant protection machine and operation control method thereof |
| CN117606477A (en) * | 2023-10-19 | 2024-02-27 | 天津大学 | Path planning method for multi-information fusion |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6445983B1 (en) * | 2000-07-07 | 2002-09-03 | Case Corporation | Sensor-fusion navigator for automated guidance of off-road vehicles |
| EP1674324A1 (en) * | 2004-12-22 | 2006-06-28 | CLAAS Selbstfahrende Erntemaschinen GmbH | Agricultural working machine |
| CN101866181A (en) * | 2009-04-16 | 2010-10-20 | 中国农业大学 | Navigation method and navigation device of agricultural machinery as well as agricultural machinery |
| US20130204437A1 (en) * | 2003-12-12 | 2013-08-08 | Vision Robotics Corporation | Agricultural robot system and method |
| CN104808660A (en) * | 2015-03-04 | 2015-07-29 | 中南大学 | Concave convex mixed complex polygon farmland unmanned aerial vehicle spraying operation flight path planning method |
| CN105980948A (en) * | 2014-02-06 | 2016-09-28 | 洋马株式会社 | Method for setting travel path of autonomous travel work vehicle |
| CN108710840A (en) * | 2018-05-10 | 2018-10-26 | 江苏大学 | A kind of farmland spray machine device people vision guided navigation path identification method |
| CN108739763A (en) * | 2018-07-12 | 2018-11-06 | 东风井关农业机械有限公司 | Fog machine and its flusher and its working method and barrier-avoiding method |
-
2019
- 2019-03-15 CN CN201910201270.1A patent/CN109885063A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6445983B1 (en) * | 2000-07-07 | 2002-09-03 | Case Corporation | Sensor-fusion navigator for automated guidance of off-road vehicles |
| US20130204437A1 (en) * | 2003-12-12 | 2013-08-08 | Vision Robotics Corporation | Agricultural robot system and method |
| EP1674324A1 (en) * | 2004-12-22 | 2006-06-28 | CLAAS Selbstfahrende Erntemaschinen GmbH | Agricultural working machine |
| CN101866181A (en) * | 2009-04-16 | 2010-10-20 | 中国农业大学 | Navigation method and navigation device of agricultural machinery as well as agricultural machinery |
| CN105980948A (en) * | 2014-02-06 | 2016-09-28 | 洋马株式会社 | Method for setting travel path of autonomous travel work vehicle |
| CN104808660A (en) * | 2015-03-04 | 2015-07-29 | 中南大学 | Concave convex mixed complex polygon farmland unmanned aerial vehicle spraying operation flight path planning method |
| CN108710840A (en) * | 2018-05-10 | 2018-10-26 | 江苏大学 | A kind of farmland spray machine device people vision guided navigation path identification method |
| CN108739763A (en) * | 2018-07-12 | 2018-11-06 | 东风井关农业机械有限公司 | Fog machine and its flusher and its working method and barrier-avoiding method |
Non-Patent Citations (9)
| Title |
|---|
| LIU HUI 等: "Spray target detection based on laser scanning sensor and real-time correction of IMU attitude angle", 《TRANSACTIONS OF THE CHINESE SOCIETY OF AGRICULTURAL ENGINEERING》 * |
| LIU PINGZENG 等: "Obstacle avoidance system for agricultural robots based on multi-sensor information fusion", 《PROCEEDINGS OF 2011 INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY》 * |
| NOBORU NOGUCHI 等: "Autonomous agricultural tractor with an intelligent navigation system", 《4TH IFAC SYMPOSIUM ON INTELLIGENT AUTONOMOUS VEHICLES》 * |
| NORASHIKIN M. THAMRIN 等: "Simultaneous localization and mapping based real-time inter-row tree tracking technique for unmanned aerial vehicle", 《2012 IEEE INTERNATIONAL CONFERENCE ON CONTROL SYSTEM, COMPUTING AND ENGINEERING》 * |
| SUBRAMANIAN VIJAY 等: "Development of machine vision and laser radar based autonomous vehicle guidance systems for citrus grove navigation", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》 * |
| 刘美辰: "农机作业障碍物检测与避障方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 张国远: "高地隙自走式平台四轮转向系统的研究和设计", 《中国优秀硕士学位论文全文数据库农业科技辑》 * |
| 徐博 等: "多架次作业植保无人机最小能耗航迹规划算法研究", 《农业机械学报》 * |
| 陈艳 等: "基于GPS和机器视觉的组合导航定位方法", 《农业工程学报》 * |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110296698A (en) * | 2019-07-12 | 2019-10-01 | 贵州电网有限责任公司 | It is a kind of with laser scanning be constraint unmanned plane paths planning method |
| CN110609570A (en) * | 2019-07-23 | 2019-12-24 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Autonomous obstacle avoidance inspection method based on unmanned aerial vehicle |
| CN110411452A (en) * | 2019-08-12 | 2019-11-05 | 西北农林科技大学 | A kind of farmland spray machine device people's navigation path identification method based on binocular vision |
| CN110426045A (en) * | 2019-08-12 | 2019-11-08 | 西北农林科技大学 | A kind of farmland spray machine device people vision guided navigation parameter acquiring method |
| CN110428664A (en) * | 2019-09-09 | 2019-11-08 | 湖南科技大学 | Traffic avoiding collision based on computer vision human bioequivalence |
| CN111007850A (en) * | 2019-12-06 | 2020-04-14 | 首都师范大学 | Agricultural machine control method, device and equipment based on field operation |
| CN111007850B (en) * | 2019-12-06 | 2023-06-23 | 首都师范大学 | Agricultural machine control method, device and equipment based on field operation |
| CN111596652A (en) * | 2019-12-30 | 2020-08-28 | 山东省科学院自动化研究所 | Pesticide spraying intelligent agricultural machinery path finding navigation control method and system |
| CN111506062A (en) * | 2020-03-30 | 2020-08-07 | 江苏大学 | Full-automatic pesticide applying ship and uniform pesticide spraying method |
| CN111506062B (en) * | 2020-03-30 | 2021-02-12 | 江苏大学 | Full-automatic pesticide applying ship and uniform pesticide spraying method |
| CN111506105A (en) * | 2020-04-08 | 2020-08-07 | 安徽舒州农业科技有限责任公司 | Agricultural unmanned aerial vehicle control device and sowing control method |
| CN111796283A (en) * | 2020-07-13 | 2020-10-20 | 江苏恒澄交科信息科技股份有限公司 | Millimeter wave radar noise reduction method based on route |
| CN112000131A (en) * | 2020-09-09 | 2020-11-27 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster path planning method and system based on artificial potential field method |
| CN112000131B (en) * | 2020-09-09 | 2022-08-02 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster path planning method and system based on artificial potential field method |
| CN112526983A (en) * | 2020-09-11 | 2021-03-19 | 深圳市银星智能科技股份有限公司 | Robot path planning method, master control chip and robot |
| CN112526983B (en) * | 2020-09-11 | 2022-10-28 | 深圳银星智能集团股份有限公司 | Robot path planning method, master control chip and robot |
| CN112596518A (en) * | 2020-12-07 | 2021-04-02 | 深圳拓邦股份有限公司 | Robot cleaning path planning method and device and floor washing robot |
| CN113179826A (en) * | 2021-04-30 | 2021-07-30 | 梁世军 | Application technology of pesticide on water surface |
| CN113112209A (en) * | 2021-05-13 | 2021-07-13 | 浙江万里学院 | Logistics distribution safety protection method for acquiring real-time movement track of goods |
| CN113112209B (en) * | 2021-05-13 | 2024-03-26 | 浙江万里学院 | Logistics distribution safety protection method for acquiring real-time motion trail of goods |
| CN113459090A (en) * | 2021-06-15 | 2021-10-01 | 中国农业大学 | Intelligent obstacle avoiding method of palletizing robot, electronic equipment and medium |
| CN113778081B (en) * | 2021-08-19 | 2022-07-22 | 中国农业科学院农业资源与农业区划研究所 | Orchard path identification method and robot based on laser radar and vision |
| CN113778081A (en) * | 2021-08-19 | 2021-12-10 | 中国农业科学院农业资源与农业区划研究所 | Orchard path identification method and robot based on laser radar and vision |
| CN113799129A (en) * | 2021-09-17 | 2021-12-17 | 吉林省农业机械研究院 | Barrier control system is kept away to spray lance formula laxative machine arm intelligence |
| CN113791625A (en) * | 2021-09-30 | 2021-12-14 | 深圳市优必选科技股份有限公司 | Full coverage path generation method and device, terminal equipment and storage medium |
| CN114326717A (en) * | 2021-12-13 | 2022-04-12 | 中国科学院计算技术研究所 | Intelligent agricultural machinery transition and operation fusion path planning method and system |
| CN114680097B (en) * | 2022-06-02 | 2022-08-09 | 农业农村部南京农业机械化研究所 | Sprayer pesticide application positioning method based on monitoring data acquisition and processing |
| CN114680097A (en) * | 2022-06-02 | 2022-07-01 | 农业农村部南京农业机械化研究所 | Spraying machine pesticide application positioning method based on monitoring data acquisition and processing |
| CN116225072A (en) * | 2023-05-09 | 2023-06-06 | 济宁市兖州区同瑞机械有限公司 | Route real-time planning management system suitable for agricultural transport machine |
| CN116609278A (en) * | 2023-07-21 | 2023-08-18 | 华东交通大学 | Method and system for collecting farmland heavy metal spectrum data |
| CN116609278B (en) * | 2023-07-21 | 2023-10-17 | 华东交通大学 | Method and system for collecting farmland heavy metal spectrum data |
| CN116965393A (en) * | 2023-09-22 | 2023-10-31 | 安徽农业大学 | High-clearance variable-track plant protection machine and operation control method thereof |
| CN116965393B (en) * | 2023-09-22 | 2024-01-12 | 安徽农业大学 | High-clearance variable-track plant protection machine and operation control method thereof |
| CN117606477A (en) * | 2023-10-19 | 2024-02-27 | 天津大学 | Path planning method for multi-information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109885063A (en) | A kind of application robot farmland paths planning method merging vision and laser sensor | |
| CN103891697B (en) | The variable spray method of a kind of indoor autonomous spraying machine device people | |
| EP3119178B1 (en) | Method and system for navigating an agricultural vehicle on a land area | |
| US9603300B2 (en) | Autonomous gardening vehicle with camera | |
| US20190381529A1 (en) | Device for Printing Images on Floor Surfaces | |
| CN109471434B (en) | Novel variable spray path planning autonomous navigation system and method | |
| WO2017092904A1 (en) | Path planning for area coverage | |
| CN109032174B (en) | Unmanned aerial vehicle operation route planning method and operation execution method | |
| CN110254722A (en) | A kind of aerocraft system and its method, the product with computer program | |
| CN108716919A (en) | Plant protection drone path planning method based on arbitrary polygon clear area | |
| CN115143964A (en) | Four-footed robot autonomous navigation method based on 2.5D cost map | |
| Bakker | An autonomous robot for weed control: design, navigation and control | |
| CN111830968B (en) | Multifunctional water shield unmanned operation ship and navigation control method thereof | |
| CN108196538A (en) | Field robots autonomous navigation system and method based on three-dimensional point cloud model | |
| Ribeiro et al. | 3D monitoring of woody crops using an unmanned ground vehicle | |
| Rasmussen et al. | Trail following with omnidirectional vision | |
| CN115097833A (en) | Automatic obstacle avoidance method and system for pesticide application robot and storage medium | |
| Hrabar et al. | Towards autonomous navigation of a mobile robot in a steep slope vineyard | |
| CN113587946A (en) | Visual navigation system and method for field agricultural machine | |
| Hutsol et al. | Robotic technologies in horticulture: analysis and implementation prospects | |
| AHAMED et al. | Navigation using a laser range finder for autonomous tractor (part 1) positioning of implement | |
| de Lima et al. | Air-ground collaborative localisation in forests using lidar canopy maps | |
| Andersen | Mobile robot navigation | |
| Bengochea-Guevara et al. | An Autonomous Guided Field Inspection Vehicle for 3D Woody Crops Monitoring | |
| Jalajamony et al. | Low-cost thermal infrared aided drone for dry patch detection in an intelligent irrigation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |